Name
Abstract | ||
|---|---|---|
In this paper, we present a new perspective towards image-based shape generation. Most existing deep learning based shape reconstruction methods employ a single-view deterministic model which is sometimes insufficient to determine a single groundtruth shape because the back part is occluded. In this work, we first introduce a conditional generative network to model the uncertainty for single-view reconstruction. Then, we formulate the task of multi-view reconstruction as taking the intersection of the predicted shape spaces on each single image. We design new differentiable guidance including the front constraint, the diversity constraint, and the consistency loss to enable effective single-view conditional generation and multi-view synthesis. Experimental results and ablation studies show that our proposed approach outperforms state-of-the-art methods on 3D reconstruction test error and demonstrates its generalization ability on real world data. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/CVPR.2019.00988 | 2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) |
Field | DocType | Volume |
Computer vision,Pattern recognition,Computer science,Stereo reconstruction,Differentiable function,Deterministic system,Artificial intelligence,Generative grammar,Deep learning,Shape reconstruction,3D reconstruction | Journal | abs/1904.06699 |
ISSN | Citations | PageRank |
1063-6919 | 5 | 0.43 |
References | Authors | |
0 | 5 | |